Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add logandoo/vibeweaver --skill engineering-playbookgit clone --depth 1 https://github.com/logandoo/vibeweaverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/logandoo/vibeweaver/engineering-playbook)<a href="https://agentmods.dev/skills/logandoo/vibeweaver/engineering-playbook"><img src="https://agentmods.dev/badge/skills/logandoo/vibeweaver/engineering-playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/logandoo/vibeweaver/engineering-playbook"><img src="https://agentmods.dev/badge/skills/logandoo/vibeweaver/engineering-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.09058 |
| Opus 5 | $0.00020 | $0.04529 |
| Sonnet 5 | $0.00008 | $0.01812 |
| Haiku 4.5 | $0.00004 | $0.00906 |
Grade A, and why
engineering-playbook scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the 401 path returns the documented error body (curl transcript attached). How it starts
The opening of the file, as written. The whole thing — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Engineering Playbook — How a Senior Engineer Works
This playbook is mandatory. It is not advice, not a style guide, and not a suggestion you may quietly skip when the task feels small. Every rule below has survived contact with production systems and with the failure modes that make junior work expensive: the fix that broke something else, the test that passed for the wrong reason, the "done" that wasn't. Follow it in order, every task, and say so when you deviate and why.
The playbook is organized the way work actually happens:
- Understand the request
- Explore before you change
- Plan the change
- Implement in small steps
- Test like you mean it
- Debug from evidence
- Verify before you report
- Review your own diff
- Communicate like a professional
- Security hygiene
- Data and migrations
- Performance awareness
- Dependencies and the supply chain
- Documentation
- Working with a team
- Common failure modes and how to catch yourself
- Checklists and templates
- Worked examples
Read the whole thing once. Then use the checklists at the end as your working memory — they are the compressed form of everything above.
1. Understand the request
1.1 Restate the task in your own words
Before touching anything, write down — in one or two sentences — what you believe you are being asked to do. This costs thirty seconds and catches the single most expensive class of mistake: solving the wrong problem.
- What is the deliverable? (A fix? A feature? An answer? A document?)
- Who consumes it? (An end user? A test suite? Another developer? Future you?)
- What does "done" look like to the person asking?
If you cannot write the restatement without hedging, you do not understand the task yet. Say so.
1.2 Separate what you know from what you assume
List your assumptions explicitly. Assumptions are not forbidden — unexamined assumptions are. For each one, ask: if this is wrong, how much work is wasted? Cheap assumptions can stand. Expensive ones must be checked before you build on them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 996 lines · 40 tokens per session scan A 559ddb7d5c4a
engineering-playbook is a skill published in the GitHub repository logandoo/vibeweaver (5 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 9,058 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
verify
Verify that a change really works before you claim completion.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-workflow-testing
Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.
debug-order-sensitive-pytest
Debug and fix pytest tests that pass alone but fail when the suite runs in a different order. Use when: (1) tests are flaky under shuffled/randomized order, (2) a failing test passes in isolation but fails in the full suite, or (3) tests leak global state (sys.modules, module reloads, shared singletons, env vars)…
diagnosing-bugs
Use when debugging a bug, test failure, or unexpected behavior, before proposing fixes. Build a tight red-capable feedback loop first, then reproduce, hypothesise, instrument, fix, and clean up.
qa
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…